© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 19796
    Prev
    Next
    INDEX
    Explanations

    question or description starters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     of
    -3.13
     he
    -2.80
     are
    -2.56
    鉝
    -2.47
    噤
    -2.31
     suave
    -2.31
    </strong>
    -2.31
    ↵↵
    -2.28
     erhielten
    -2.23
    唬
    -2.23
    POSITIVE LOGITS
    When
    2.91
    錞
    2.67
     icône
    2.63
    There
    2.53
     Makes
    2.50
    Despite
    2.36
    The
    2.30
     Surprisingly
    2.30
     Giving
    2.22
    鏨
    2.22
    Activations Density 0.000%

    No Known Activations